Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add moeru-ai/auv --skill auv-wayland-renderinggit clone --depth 1 https://github.com/moeru-ai/auvWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/moeru-ai/auv/auv-wayland-rendering)<a href="https://agentmods.dev/skills/moeru-ai/auv/auv-wayland-rendering"><img src="https://agentmods.dev/badge/skills/moeru-ai/auv/auv-wayland-rendering/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/moeru-ai/auv/auv-wayland-rendering"><img src="https://agentmods.dev/badge/skills/moeru-ai/auv/auv-wayland-rendering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 153 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00107 | $0.01472 |
| Opus 5 | $0.00053 | $0.00736 |
| Sonnet 5 | $0.00021 | $0.00294 |
| Haiku 4.5 | $0.00011 | $0.00147 |
Grade A, and why
auv-wayland-rendering scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AUV Wayland Rendering
Build a reproducible Linux desktop session in which AUV can observe a Wayland display and persist capture artifacts. Treat environment validation as evidence, not as a change to AUV's public support claim.
Keep ownership explicit: the compositor renders application clients; AUV requests frames through the portal and records them. Do not imply that AUV ships the compositor or a Linux overlay renderer.
Read the relevant references
- Read setup.md before installing packages, creating a compositor session, or configuring remote viewing.
- Read troubleshooting.md when a probe or capture fails, the image is blank, or hardware rendering is uncertain.
- Check AUV's current support matrix before
describing a result as supported. A successful live probe is
live-validatedevidence for the named environment only.
Follow the workflow
1. Inspect before changing the host
Run the read-only probe in the target shell:
.agents/skills/auv-wayland-rendering/scripts/probe-wayland.sh
Add --require-gpu to make missing GPU prerequisites fatal when hardware
rendering is required. The flag does not replace compositor-log evidence.
Record:
- distribution and package manager;
- existing compositor and whether the session is local, nested, or headless;
WAYLAND_DISPLAY,XDG_RUNTIME_DIR, and the session D-Bus;- accessible
/dev/dri/renderD*nodes and the renderer reported by compositor logs oreglinfo/vulkaninfo; - ScreenCast portal and PipeWire readiness.
Do not infer GPU rendering from the presence of a GPU or render node. Require a
renderer log or renderer-tool result. Label pixman, llvmpipe, and similar
paths as software rendering.
2. Choose the session shape
Prefer the existing logged-in Wayland compositor when one is available. It already owns the seat, GPU, D-Bus activation environment, and user consent UI.
Use headless Sway when the host has no desktop session or the test must be
isolated. Start with wlroots renderer auto-selection. Force pixman only as an
explicit software fallback; doing so gives deterministic rendering but does
not validate the GPU path.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 159 lines · 107 tokens per session scan A 473f9f57054c
auv-wayland-rendering is a skill published in the GitHub repository moeru-ai/auv (27 stars, last pushed 2d ago), licensed Apache-2.0. It adds 107 tokens to every session and 1,472 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other skills, from other repositories
gke-ai-troubleshooting-tpu-dynamic-slices-monitoring
Monitors, troubleshoots, and manages GKE TPU Dynamic Slices custom resources. Use when checking TPU slice lifecycle states, troubleshooting slice provisioning failures, validating single-slice or multi-slice (JobSet) workload manifests, or safely patching stuck finalizers and disabling the slice controller. Don't use…
gke-ai-troubleshooting-tpu-vbar-oom
Diagnoses and prevents vbarcontrolagent segfaults, out-of-memory (OOM) errors, and TPU device initialization failures on TPU v6e nodes in GKE caused by race conditions during TPU device resets or high-frequency metrics polling. Use when troubleshooting vbarcontrolagent crashes, memory cgroup OOMs in serial console…
doca-flow
Build and debug DOCA Flow applications on supported NVIDIA NICs/DPUs: define match/action pipes, initialize ports and representors, choose forwarding targets, validate pipes before hardware programming, read counters, match the Flow version to the installed DOCA release, and diagnose Flow API errors. Trigger on DOCA…
diagnose-driver-install
Diagnose NVIDIA driver installation failures on DeepOps-managed nodes — nvidia-smi errors, "No devices were found", DKMS build failures, or GPU pods crash-looping. Use before reinstalling anything.
agentsight-bugfix
A five-stage workflow for fixing bugs in AgentSight: understand the report, reproduce the problem, find its cause, make a small code change, and verify the result. AgentSight is a system that observes and analyses agent activity.
openhue
Control Philips Hue lights/scenes via the OpenHue CLI.